continuation_benchmark/both_metric_eval/per_plasmid_completion.csv

Plasmid,Archetype,Base_mean,Base_n,SFT_mean,SFT_n,RL_mean,RL_n,RL_minus_SFT,RL_minus_Base,length_bp,gc,cds_count,ori_family,amr,description
AB444682.1,coryne_integration,-7.470820569992066,10,-8.806614708900451,10,-7.7183595418930055,10,1.0882551670074454,-0.24753897190093976,4051,0.519,3,unannotated,CmR,"Shuttle vector pCRB1 DNA, complete sequence"
AB610285.1,p15A_compact,-5.538560353792631,13,-5.838592850244963,13,-7.485453403913057,13,-1.6468605536680947,-1.9468930501204262,4916,0.548,2,R6K,CmR,"R6K-based suicide vector pUT399-abrB DNA, complete sequence"
AF327713.1,thermus_pIOK,-3.9692203672311734,16,-3.8907192540827964,16,-6.216196965426207,16,-2.32547771134341,-2.246976598195033,5329,0.618,4,RK2|F/oriV,ZeoR,"Cloning vector pCM51, complete sequence"
AJ439603.2,mob_F_oriV,-8.060953617095947,7,-8.579597268785749,7,-8.464121273585729,7,0.11547599520002017,-0.4031676564897815,2660,0.53,1,unannotated,HygR,"Synthetic construct for chimaeric Cloning vector pSPUTK multiple cloning site, Aspergillus nidulans "
AY299696.1,mob_F_oriV,-3.6043178136460483,18,-3.013746362780997,18,-6.055320961607827,18,-3.04157459882683,-2.451003147961779,5938,0.574,1,pBBR1|F/oriV,SpecR,"Broad host range expression vector pMHE5, complete sequence"
AY613991.1,thermus_pIOK,-14.54097318649292,10,-7.0869037985801695,10,-10.195262622833251,10,-3.1083588242530817,4.345710563659669,4663,0.523,2,pUC/ColE1,AmpR|HygR,"Cloning vector pSRalphahygro, complete sequence"
BD006803.1,BD_patent_sparse,-7.717248630523682,5,-7.768001556396484,5,-7.763212394714356,5,0.004789161682128729,-0.04596376419067383,1815,0.522,0,unannotated,ZeoR,"L-ricin-producible corynebacteria, replicable DNA among them, process for producing L-ricin, and str"
DI020703.1,BD_patent_sparse,-8.295118515308086,13,-8.011643409729004,13,-8.511060788081242,13,-0.49941737835223776,-0.21594227277315525,4369,0.583,0,unannotated,ZeoR,Plasmid autonomously replicable in Coryneform bacterium
E10961.1,mob_F_oriV,-6.5943514960152765,7,-5.989927325929914,7,-7.60520601272583,7,-1.6152786867959161,-1.0108545167105536,2476,0.578,0,unannotated,KanR,Plasmid DNA containing a reproduction and proliferation region and a Kanamycin resistant region
EU679507.1,mob_F_oriV,-5.886256071958034,17,-3.9369937236804295,17,-7.144005508983836,17,-3.207011785303407,-1.2577494370258027,8170,0.561,2,RK2|pUC/ColE1|F/oriV,KanR,"Expression vector pHC60, complete sequence"
HQ908071.1,mob_F_oriV,-6.041856608783396,13,-4.9722341769016705,13,-7.299550377405607,13,-2.3273162005039367,-1.257693768622211,4384,0.51,3,R6K|F/oriV,AmpR|KanR,"Cloning vector pBAM1, complete sequence"
JX456191.1,mob_F_oriV,-3.878055644407868,10,-4.3166498827748,10,-7.304956591129303,10,-2.9883067083545027,-3.4269009467214344,3839,0.558,2,R6K,KanR|ZeoR,"Cloning vector pJW3, complete sequence"
JX560390.1,p15A_compact,-8.60308082287128,13,-6.60504568540133,13,-10.00658944936899,13,-3.40154376396766,-1.4035086264977092,5840,0.543,3,RK2,SpecR,"Cloning vector pSEVA428, complete sequence"
KC537291.1,BD_patent_sparse,-10.884250852796766,9,-7.698847770690918,9,-9.922869152492947,9,-2.2240213818020287,0.9613817003038196,4785,0.486,1,unannotated,ZeoR,"Cloning vector pG-Sable, complete sequence"
KM403115.1,p15A_compact,-2.8458242366115365,14,-2.398422686860223,14,-5.55663081577846,14,-3.158208128918237,-2.7108065791669236,4546,0.516,3,R6K,AmpR|GmR,"Cloning vector pBAMD1-6, complete sequence"
KX709879.1,BD_patent_sparse,-3.3959262864508974,15,-2.621740067160378,15,-6.531683611869812,15,-3.9099435447094337,-3.1357573254189144,5419,0.594,2,unannotated,ZeoR,"Cloning vector pSET152 Ble (ble) and phi31 integrase genes, complete cds"
KX714576.1,mob_F_oriV,-5.130742144584656,5,-3.276125378839788,5,-6.411407518386841,5,-3.1352821395470527,-1.2806653738021847,2570,0.553,1,unannotated,KanR,"Cloning vector pKMAG, complete sequence"
KY368389.1,p15A_compact,-2.0506204262686274,15,-2.172025562952816,15,-5.719194010893504,15,-3.5471684479406878,-3.6685735846248764,4811,0.553,3,pBBR1,ErmR,"Cloning vector pBBR1MCS-Erm, complete sequence"
L36849.1,p15A_compact,-8.573824644088745,8,-5.729884564876556,8,-9.138205230236053,8,-3.408320665359497,-0.5643805861473083,3451,0.528,1,pUC/ColE1,ZeoR,"Cloning vector pZEO (isolate SV1) phleomycin/zeocin-binding protein gene, complete cds"
LC727554.1,coryne_integration,-6.616098813712597,8,-3.5773435748997144,8,-8.981073319911957,8,-5.403729745012242,-2.36497450619936,4080,0.503,2,unannotated,KanR,"Schizosaccharomyces pombe vector pEDIT379N DNA, complete sequence"
LC792545.1,thermus_pIOK,-6.7950690852271185,18,-5.4965773721536,18,-7.618886947631836,18,-2.122309575478236,-0.8238178624047174,6981,0.514,3,RK2|pUC/ColE1|F/oriV,HygR,"Expression vector pT5exRKH DNA, complete sequence"
LC823835.1,BD_patent_sparse,-9.181110284545206,11,-6.911814657124606,11,-8.309260151603006,11,-1.3974454944783998,0.8718501329421997,4099,0.443,3,unannotated,ZeoR,"Expression vector pSD128 DNA, complete sequence"
LC895502.1,BD_patent_sparse,-7.345466068812779,7,-6.986620845539229,7,-8.037310344832283,7,-1.0506894992930542,-0.6918442760195047,2768,0.535,1,pUC/ColE1,HygR|ZeoR,"Escherichia coli plasmid vector pHSG298Hg DNA, complete sequence"
LT743407.1,p15A_compact,-12.558914721012115,8,-8.513788521289825,8,-10.189039051532745,8,-1.67525053024292,2.36987566947937,3501,0.535,2,pUC/ColE1,SpecR,"Human ORFeome Gateway entry vector pENTR223-MOB2, complete sequence"
LY657134.1,BD_patent_sparse,-9.112232387065887,12,-5.268065705895424,12,-9.010643323262533,12,-3.7425776173671093,0.10158906380335431,5014,0.408,0,unannotated,ZeoR,"KR 1020190061534-A/10: SHUTTLE PLASMID REPLICABLE IN CLOSTRIDIUM AND ESCHERICHIA COLI, AND RECOMBINA"
LY657138.1,BD_patent_sparse,-6.148536508733576,11,-3.248260023580356,11,-7.532336495139382,11,-4.284076471559025,-1.3837999864058057,4060,0.404,0,unannotated,ZeoR,"KR 1020190061534-A/14: SHUTTLE PLASMID REPLICABLE IN CLOSTRIDIUM AND ESCHERICHIA COLI, AND RECOMBINA"
MG100204.1,coryne_integration,-9.67737987306383,9,-7.211830629242791,9,-9.816648165384928,9,-2.6048175361421366,-0.13926829232109839,5004,0.557,2,unannotated,KanR,"Expression vector pARKANI, complete sequence"
MH286806.1,thermus_pIOK,-7.45812991177305,13,-5.353102843205516,13,-7.857594847679138,13,-2.5044920044736223,-0.3994649359060878,6180,0.543,3,pUC/ColE1,AmpR|HygR,"Fungal transformation vector pKT313, complete sequence"
MH488942.1,p15A_compact,-7.278368431329727,20,-6.051445062481799,20,-8.626486390829086,20,-2.5750413283472877,-1.3481179594993593,7194,0.546,3,p15A,KanR,"Cloning vector pTac-VvSTS-Sc4CLm, complete sequence"
MK697351.1,coryne_integration,-6.687463267531712,8,-4.108586445698165,8,-8.196327283978462,8,-4.087740838280297,-1.5088640164467506,3986,0.572,3,unannotated,KanR,"Broad host range vector pIND, complete sequence"
MN450166.1,mob_F_oriV,-5.900682670729501,7,-5.709946274757385,7,-8.419466427394322,7,-2.7095201526369372,-2.5187837566648215,2392,0.475,1,R6K|F/oriV,KanR,"Synthetic construct plasmid pGEung, complete sequence"
MT304465.1,coryne_integration,-5.936243963028703,14,-5.626759409974901,14,-9.448746476854597,14,-3.8219870668796956,-3.5125025138258934,5358,0.545,3,unannotated,TetR|GmR,"Cloning vector pRGPDuo1, complete sequence"
MT684463.1,p15A_compact,-3.95341751405171,7,-3.7535418612616405,7,-5.996974638530186,7,-2.2434327772685454,-2.043557124478476,4641,0.516,1,pUC/ColE1,ZeoR,"Cloning vector pAS_HO_natNT2, complete sequence"
MW059023.1,p15A_compact,-9.31601087252299,18,-8.75516488817003,18,-8.677263418833414,18,0.07790146933661646,0.6387474536895752,6938,0.505,5,p15A,CmR|SpecR,"Expression vector pGED, complete sequence"
OP627880.1,thermus_pIOK,-10.129285424947739,16,-9.075650125741959,16,-10.15181690454483,16,-1.0761667788028717,-0.022531479597091675,7840,0.564,4,pBR322|pUC/ColE1,SpecR,"Cloning vector pJLG029_pRA301_T7_dsbA-pruR-3XFLAG, complete sequence"
OP654169.1,p15A_compact,-7.119560062885284,8,-6.248482406139374,8,-8.002444565296173,8,-1.7539621591567993,-0.8828845024108887,3222,0.462,2,p15A,TetR,"Cloning vector pRW12, complete sequence"
OR043017.1,thermus_pIOK,-5.360395261952791,17,-4.242003971941064,17,-6.3561307191848755,17,-2.1141267472438114,-0.9957354572320849,5906,0.551,3,pBBR1|RK2,HygR,"Vector pHBA010_BASIS-components_pH_3-prime, complete sequence"
OR900360.1,thermus_pIOK,-6.481880457628341,21,-5.268755296866099,21,-8.20636601107461,21,-2.9376107142085113,-1.7244855534462697,7605,0.562,7,RK2|pBR322|pUC/ColE1|F/oriV,GmR,"Cloning vector pHERD99_par, complete sequence"
PP391868.1,p15A_compact,-7.271414800123735,11,-6.68164726820859,11,-8.296475670554422,11,-1.6148284023458315,-1.0250608704306865,3915,0.51,2,R6K,TetR|ZeoR,"Cloning vector pGPS-Zeo-rox plasmid pGPS-Zeo-rox, complete sequence"
PQ361717.1,thermus_pIOK,-4.590262294816057,16,-4.40279389533498,16,-6.749451459385455,16,-2.3466575640504743,-2.1591891645693977,5788,0.637,4,RK2|pBR322|pUC/ColE1,GmR,"Cloning vector pIJ86, complete sequence"
PQ511365.1,p15A_compact,-5.970262659447534,14,-5.299263806215355,14,-7.646927995341165,14,-2.34766418912581,-1.676665335893631,4871,0.517,3,p15A,CmR,"Cloning vector p15a-FKSL-FA2YQR, complete sequence"
PQ738616.1,coryne_integration,-1.7952449217361088,12,-1.7505826349758233,12,-6.266551971435547,12,-4.515969336459723,-4.471307049699438,4292,0.48,3,unannotated,AmpR|KanR,"Cloning vector pBAMD1.2, complete sequence"
PV368681.1,BD_patent_sparse,-9.082999730110169,10,-5.900775456428528,10,-9.533542966842651,10,-3.632767510414123,-0.4505432367324822,4406,0.535,0,unannotated,ZeoR,"UNVERIFIED: Cloning vector pCR4-Zeocin-P2A, complete sequence"
PV368684.1,BD_patent_sparse,-7.756036221981049,8,-6.898588001728058,8,-8.382756859064102,8,-1.4841688573360443,-0.6267206370830536,5757,0.52,0,unannotated,ZeoR,"UNVERIFIED: Cloning vector pCR4-Pv.00443#1uH-P2A-ZeocinR-P2A-Or47a, complete sequence"
PX861354.1,coryne_integration,-8.897505474090575,10,-8.51731276512146,10,-9.092171144485473,10,-0.574858379364013,-0.19466567039489746,4134,0.519,2,unannotated,CmR,"Cloning vector pR1RCm, complete sequence"
RBZS01000460.1,BD_patent_sparse,-8.105709489186605,15,-7.8751169840494795,15,-8.210100491841635,15,-0.33498350779215524,-0.10439100265502965,4896,0.583,4,unannotated,ZeoR,"Sodalis-like symbiont of Bactericera trigonica isolate IL scaffold_3467, whole genome shotgun sequen"
U03497.1,BD_patent_sparse,-8.240781390004688,18,-6.574405829111735,18,-10.177187323570251,18,-3.602781494458516,-1.9364059335655632,8259,0.449,0,unannotated,ZeoR,"Yeast centromere vector pBM272 with inducible GAL promoter, complete sequence"